Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.5914. Min Act: -0.1700
Data Index: 8330482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.5914. Min Act: -0.1700
Data Index: 5804875 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.5758. Min Act: -0.1700
Data Index: 7032915 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.5132. Min Act: -0.1700
Data Index: 6154823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4975. Min Act: -0.1700
Data Index: 8051552 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 4673265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 1604135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 5926919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 2969181 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 2115910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 1979868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 7840866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 3067516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 601292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4818. Min Act: -0.1700
Data Index: 3085540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4505. Min Act: -0.1700
Data Index: 7866475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4662. Min Act: -0.1700
Data Index: 4542852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4662. Min Act: -0.1700
Data Index: 8679964 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4348. Min Act: -0.1700
Data Index: 8579453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5914. Min Range: -3.5914
Max Act: 3.4505. Min Act: -0.1700
Data Index: 3449059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19